WO2022193170A1

WO2022193170A1 - Stay identification evaluation method and system for mobile phone signaling data, and terminal and storage medium

Info

Publication number: WO2022193170A1
Application number: PCT/CN2021/081288
Authority: WO
Inventors: 尹凌; 任倩茹
Original assignee: 中国科学院深圳先进技术研究院
Priority date: 2021-03-17
Filing date: 2021-03-17
Publication date: 2022-09-22

Abstract

The present application relates to a stay identification evaluation method and system for mobile phone signaling data, and a terminal and a storage medium. The method comprises: collecting mobile phone signaling data of a travel target in a travel area and corresponding GPS data; identifying a stay activity of the travel target in the travel area on the basis of the mobile phone signaling data and by using a stay identification algorithm; and constructing a progressive stay identification evaluation system with regard to a spatiotemporal sampling characteristic of the mobile phone signaling data, and evaluating a stay activity identification result of the travel target by means of the GPS data and the stay identification evaluation system. According to embodiments of the present application, a noise characteristic and an interference source of mobile phone signaling data during stay identification can be fully considered, systematic verification and evaluation are provided for a stay identification algorithm for mobile phone signaling data, and key technical support is provided for many studies based on mobile phone signaling data.

Description

A method, system, terminal and storage medium for stop identification evaluation for mobile phone signaling data

technical field

The present application belongs to the technical field of mobile phone signaling data processing, and in particular, relates to a method, system, terminal and storage medium for staying identification and evaluation of mobile phone signaling data.

Background technique

Mobile phone signaling data is the communication data between mobile phone users and transmitting base stations or micro-stations, and it has become the most mainstream big data source. At present, research on mobile phone signaling data emerges one after another, but the mobile phone signaling data does not clearly indicate the user's activity start time, activity end time, activity location and other stay activity information. Activity information is processed. Mobile phone signaling data is collected based on communication base station positioning technology. Due to the particularity of this sampling, data sampling is uneven and data noise is caused, which greatly increases the difficulty and error of staying activity identification.

A set of targeted evaluation methods is needed to verify the effect of the stay recognition algorithm on the recognition of stay activities in the mobile phone signaling data. In the existing research on mobile phone signaling data, most of the evaluation methods for the effect of staying activity recognition are only based on subjective perception as a reference, and only a small number of studies use the job and residence data in the census to evaluate the reliability of mobile phone signaling data. verify. However, considering the diversity of human travel activities, it is not universal to use only job and residence data for stop identification assessment. At the same time, due to the limitation of data collection and privacy protection, it is difficult for the above research to obtain the real verification data set corresponding to the mobile phone signaling data, and it is impossible to realize the reliability verification by means of the correct stop point of the individual. However, none of the existing public datasets can be used as the data support for the stay identification algorithm of mobile phone signaling data. Therefore, it is necessary to provide a set of evaluation systems for the characteristics of mobile phone signaling data to provide key technical support for many researches based on mobile phone signaling data.

SUMMARY OF THE INVENTION

The present application provides a method, system, terminal and storage medium for staying identification evaluation of mobile phone signaling data, aiming to solve one of the above-mentioned technical problems in the prior art at least to a certain extent.

In order to solve the above problems, the application provides the following technical solutions:

A stop identification evaluation method for mobile phone signaling data, comprising:

Collect the mobile phone signaling data and the corresponding GPS data of the travel target in the travel area;

Based on the mobile phone signaling data, a stay identification algorithm is used to identify the stay activity of the travel target in the travel area;

According to the time-space sampling characteristics of mobile phone signaling data, a progressive stop recognition evaluation system is constructed, and the stop activity recognition result of the travel target is evaluated through the GPS data and the stop recognition evaluation system.

The technical solution adopted in the embodiment of the present application further includes: the collected mobile phone signaling data of the travel target in the travel area and the corresponding GPS data are specifically:

Obtain GPS data of the travel target through a mobile phone positioning system or a GPS locator.

The technical solutions adopted in the embodiments of the present application further include: the collection of mobile phone signaling data and corresponding GPS data of the travel target in the travel area further includes:

The stay activity in the GPS data is marked according to the travel log of the travel target, and the mobile phone signaling data is preprocessed in combination with the GPS data; the preprocessing includes the processing of the mobile phone signaling data. Missing, redundant, or/and discrete points are imputed or discarded.

According to the base station distribution data in the travel area, the cell phone signaling data and the GPS data are checked by the base station unit, the abnormal values outside the travel area in the mobile phone signaling data and the GPS data are deleted, and the Statistical characteristics of GPS data in time and space;

The statistical features at the time level include travel activity type distribution, travel activity time distribution, and stay activity time distribution;

The statistical features at the spatial level include the spatial distribution of stay locations and the spatial distribution of travel distances.

The technical solution adopted in the embodiment of the present application further includes: the stay identification algorithm includes SMoT, SMUoT or TwoStages&MAD.

The technical solution adopted in the embodiment of the present application further includes: constructing a progressive stop recognition evaluation system according to the spatiotemporal sampling characteristics of mobile phone signaling data, and using the GPS data and the stop recognition evaluation system to determine the stop activity of the travel target The identification results are evaluated as follows:

Select the application scenario, evaluation method, evaluation index and evaluation parameter for the mobile phone signaling data stop identification to construct a stop identification evaluation system for the mobile phone signaling data stop identification algorithm, respectively from the space discrimination, space-time state discrimination and Space-time object discrimination evaluates the staying activity recognition results from three perspectives;

The spatial discrimination is used to judge whether the stay space position of the travel target in the stay activity is correct; the evaluation method of the spatial discrimination is to determine whether the spatial range of the stop point identified by the stop recognition algorithm and the correct stop point are adjacent. , the evaluation index of the spatial discrimination is the proportion of the number of correct stop point samples within a given spatial range;

The space-time state discrimination is used to identify the stay space position of the travel target in the stay activity and the proportion of the corresponding stay duration; Whether the spatial range of the stop point and the correct stop point is adjacent, and the ratio of the length of stay of the identified stop point to the duration of the whole day; the evaluation index of the space-time state discrimination is the number of samples of the correct stop point in the given spatial range. The proportion and the proportion of the cumulative duration of the stay activity at the correct stop point;

The space-time object discrimination is used to identify the stop space position and stop start and end time of the travel target in the stop activity; the evaluation method of the space-time object discrimination is to determine the difference between the stop point and the stop point identified by the stop recognition algorithm. The spatial range of the correct stop point and whether the stop start and end times are adjacent; the evaluation index of the space-time object discrimination is the proportion of the number of correct stop point samples within a given space range and time range.

Another technical solution adopted by the embodiment of the present application is: a system for stopping identification and evaluation for mobile phone signaling data, including:

Data collection module: used to collect the mobile phone signaling data and the corresponding GPS data of the travel target in the travel area;

Stop identification module: used to identify the stop activity of the travel target in the travel area by using the stop identification algorithm based on the mobile phone signaling data;

Stay evaluation module: used to construct a progressive stay recognition evaluation system based on the spatiotemporal sampling characteristics of mobile phone signaling data, and evaluate the stay activity recognition result of the travel target through the GPS data and the stay recognition evaluation system.

Another technical solution adopted by the embodiments of the present application is: a terminal, the terminal includes a processor and a memory coupled to the processor, wherein,

The memory stores program instructions for implementing the method for evaluating the stop identification for mobile phone signaling data;

The processor is configured to execute the program instructions stored in the memory to control dwell recognition evaluation for cell phone signaling data.

Another technical solution adopted by the embodiments of the present application is: a storage medium storing program instructions executable by a processor, where the program instructions are used to execute the method for evaluating the stop identification and evaluation for mobile phone signaling data.

Compared with the prior art, the beneficial effects of the embodiments of the present application are: the method for evaluating the stop identification of mobile phone signaling data in the embodiments of the present application collects the mobile phone signaling data of the travel target and the corresponding GPS data, and is based on the mobile phone signaling data. The data uses the stop recognition algorithm to identify the stop activities of the travel target in the travel area, and according to the spatio-temporal sampling characteristics of mobile phone signaling data, a progressive stop recognition evaluation system is constructed. As well as space-time object discrimination and other perspectives, the results of stay activity recognition are evaluated. The embodiments of the present application can fully consider the noise characteristics and interference sources of mobile phone signaling data during stay identification, provide systematic verification and evaluation for mobile phone signaling data stay identification algorithms, and provide key technical support for many studies based on mobile phone signaling data.

Description of drawings

Fig. 1 is a flow chart of a method for assessing stop identification of mobile phone signaling data according to an embodiment of the present application;

FIG. 2 is a schematic structural diagram of a system for stopping identification and evaluation of mobile phone signaling data according to an embodiment of the application;

3 is a schematic structural diagram of a terminal according to an embodiment of the present application;

FIG. 4 is a schematic structural diagram of a storage medium according to an embodiment of the present application.

Detailed ways

In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application will be described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application.

Please refer to FIG. 1 , which is a flowchart of a method for evaluating a stop identification for mobile phone signaling data according to an embodiment of the present application. The method for evaluating the stop identification for mobile phone signaling data according to the embodiment of the present application includes the following steps:

S1: collect the original mobile phone signaling data of the travel target and the corresponding GPS data;

In this step, the GPS data of the travel target can be obtained through a mobile phone positioning system or a GPS locator.

S2: Mark the stay activities in the GPS data according to the travel log of the travel target, and preprocess the original mobile phone signaling data in combination with the GPS data to generate a mobile phone signaling data set and a GPS verification data set for the mobile phone signaling data;

In this step, the preprocessing performed on the original cell phone signaling data includes interpolation or abandonment of missing values, redundant values or/and discrete points of the original cell phone signaling data.

S3: According to the base station distribution data of the travel area, the cell phone signaling data set and the GPS verification data set are verified by the base station unit (that is, the outliers outside the travel area in the data set are deleted), and the GPS is calculated at the level of population mobility indicators. Verify the statistical characteristics of the dataset at the temporal and spatial levels;

In this step, the statistical characteristics of the GPS verification data set at the time level include travel activity type distribution, travel activity time distribution, and stay activity time distribution. Travel distance spatial distribution and other characteristics, and statistical characteristics are used to provide a reference for the matching distance threshold and matching time threshold for the evaluation of the identification result of the stay activity.

S4: Based on the mobile phone signaling data set, use the stop recognition algorithm to identify the stop activities of the travel target in the travel area;

In this step, the stay identification algorithm includes but is not limited to SMoT, SMUoT, TwoStages&MAD, etc., and the identified stay activity includes information such as the stay space position of the travel target, the start and end time of the stay, and the length of the stay.

S5: According to the spatiotemporal sampling characteristics of mobile phone signaling data, build a progressive stop recognition evaluation system, and evaluate the stop activity recognition results of the travel target through the GPS verification data set and the stop recognition evaluation system;

In this step, for the collection characteristics and application scenarios of mobile phone signaling data, the embodiment of the present application selects the application scenarios, evaluation methods, evaluation indicators, and evaluation parameters (including a given space range and a given time range), etc., to construct a set of mobile phone signaling data stay recognition algorithm evaluation system based on GPS data for progressive evaluation of mobile phone signaling data stay activity recognition results. As well as space-time object discrimination, the results of stay activity recognition are evaluated from three perspectives. in:

Spatial discrimination is used to determine whether the stay space position of the travel target in the stay activity is correct; the evaluation method of spatial discrimination is to determine whether the spatial range of the identified stop point and the correct stop point is adjacent (the difference between the identified stop point and the correct stop point) Whether the spatial distance between them is within the set distance range), the evaluation index is the proportion of the number of correct stop point samples within the given spatial range.

The spatial-temporal state discrimination is used to identify the spatial location of the travel target in the stay activity and the proportion of the corresponding stay duration; the evaluation method of the spatial-temporal state discrimination is to determine whether the identified stop point is adjacent to the correct stop point in space. , and the ratio of the length of stay at the identified stop points to the total time of the day. The evaluation indicators are the proportion of the number of correct stop point samples within a given space range and the proportion of the accumulative length of stay activities at the correct stop points.

The spatial-temporal object discrimination is used to identify the stop space position and stop start and end time of the travel target in the stop activity; the evaluation method of the space-time object discrimination is to determine the spatial range of the identified stop point and the correct stop point and whether the stop start and end time is not. Proximity, its evaluation index is the proportion of the number of correct stop point samples within a given spatial range and a given time range.

In order to verify the feasibility and effectiveness of the embodiments of the present application, the SMoT, SMUoT and TwoStages&MAD stay identification algorithms are reproduced on the constructed mobile phone signaling data set, and the mobile phone signaling data stay identification results are obtained; The mobile phone signaling data stay recognition algorithm evaluation system constructed in the embodiment conducts evaluations from three perspectives: space discrimination, space-time discrimination, and space-time object discrimination on the mobile phone signaling data stay recognition results, and the evaluation results show that each stay recognition algorithm The difference between the identified stop point and the active stop point of the original mobile phone signaling data provides a systematic and accurate verification evaluation for the mobile phone signaling data stop identification algorithm.

The stop identification evaluation method for mobile phone signaling data in the embodiment of the present application collects mobile phone signaling data and corresponding GPS data of the travel target, uses a stop identification algorithm based on the mobile phone signaling data to identify the stop activity of the travel target in the travel area, and Aiming at the spatio-temporal sampling characteristics of mobile phone signaling data, a progressive stop recognition evaluation system is constructed. According to the GPS data and the evaluation system, the stop activity recognition results are evaluated from multiple perspectives, such as space discrimination, space-time state discrimination, and space-time object discrimination. Evaluate. The embodiments of the present application can fully consider the noise characteristics and interference sources of mobile phone signaling data during stay identification, provide systematic verification and evaluation for mobile phone signaling data stay identification algorithms, and provide key technical support for many studies based on mobile phone signaling data.

Please refer to FIG. 2 , which is a schematic structural diagram of a system for stopping identification and evaluation of mobile phone signaling data according to an embodiment of the present application. The stop identification evaluation system 40 for mobile phone signaling data according to the embodiment of the present application includes:

Data collection module 41: used to collect mobile phone signaling data and corresponding GPS data of the travel target in the travel area;

Stop identification module 42: used to identify the stop activity of the travel target in the travel area by using the stop identification algorithm based on the mobile phone signaling data;

The stay evaluation module 43 is used for constructing a progressive stay recognition evaluation system according to the spatiotemporal sampling characteristics of the mobile phone signaling data, and evaluates the stay activity recognition result of the travel target through the GPS data and the stay recognition evaluation system.

Please refer to FIG. 3 , which is a schematic structural diagram of a terminal according to an embodiment of the present application. The terminal 50 includes a processor 51 and a memory 52 coupled to the processor 51 .

The memory 52 stores program instructions for implementing the above-mentioned method for evaluating the stay identification for mobile phone signaling data.

The processor 51 is configured to execute program instructions stored in the memory 52 to control the stay identification evaluation for the cell phone signaling data.

The processor 51 may also be referred to as a CPU (Central Processing Unit, central processing unit). The processor 51 may be an integrated circuit chip with signal processing capability. The processor 51 may also be a general purpose processor, digital signal processor (DSP), application specific integrated circuit (ASIC), off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component . A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

Please refer to FIG. 4 , which is a schematic structural diagram of a storage medium according to an embodiment of the present application. The storage medium of this embodiment of the present application stores a program file 61 capable of implementing all the above methods, wherein the program file 61 may be stored in the above-mentioned storage medium in the form of a software product, and includes several instructions to make a computer device (which may It is a personal computer, a server, or a network device, etc.) or a processor (processor) that executes all or part of the steps of the methods of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, Read-Only Memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes , or terminal devices such as computers, servers, mobile phones, and tablets.

The above description of the disclosed embodiments enables any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined in this invention may be implemented in other embodiments without departing from the spirit or scope of this invention. Thus, the present invention is not intended to be limited to the embodiments of the present invention shown, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

A method for stopping identification evaluation for mobile phone signaling data, characterized in that it comprises:

Collect the mobile phone signaling data and the corresponding GPS data of the travel target in the travel area;

Based on the mobile phone signaling data, a stop recognition algorithm is used to identify the stop activities of the travel target in the travel area; according to the spatiotemporal sampling characteristics of the mobile phone signaling data, a progressive stop recognition evaluation system is constructed. The identification evaluation system evaluates the stop activity identification result of the travel target.
The stop identification evaluation method for mobile phone signaling data according to claim 1, wherein the collected mobile phone signaling data of the travel target in the travel area and the corresponding GPS data are specifically:

Obtain GPS data of the travel target through a mobile phone positioning system or a GPS locator.
The stop identification evaluation method for mobile phone signaling data according to claim 1, wherein the collection of mobile phone signaling data and corresponding GPS data of the travel target in the travel area further comprises:

The stay activity in the GPS data is marked according to the travel log of the travel target, and the mobile phone signaling data is preprocessed in combination with the GPS data; the preprocessing includes the processing of the mobile phone signaling data. Missing, redundant, or/and discrete points are imputed or discarded.
The stop identification evaluation method for mobile phone signaling data according to claim 3, wherein the collection of mobile phone signaling data and corresponding GPS data of the travel target in the travel area further comprises:

Perform base station unit verification on the cell phone signaling data and GPS data according to the base station distribution data in the travel area, delete outliers outside the travel area in the cell phone signaling data and GPS data, and calculate the Statistical characteristics of GPS data in time and space;

The statistical features at the time level include travel activity type distribution, travel activity time distribution, and stay activity time distribution;

The statistical features at the spatial level include the spatial distribution of stay locations and the spatial distribution of travel distances.
The stay identification evaluation method for mobile phone signaling data according to claim 1, wherein the stay identification algorithm comprises SMoT, SMUoT or TwoStages&MAD.
The method for evaluation of stay identification for mobile phone signaling data according to claim 4, characterized in that, for the time-space sampling characteristics of mobile phone signaling data, a progressive stay identification evaluation system is constructed, The identification evaluation system evaluates the identification result of the stay activity of the travel target specifically as follows:

Select the application scenario, evaluation method, evaluation index and evaluation parameter for the mobile phone signaling data stop identification to construct a stop identification evaluation system for the mobile phone signaling data stop identification algorithm, respectively from the space discrimination, space-time state discrimination and Space-time object discrimination evaluates the staying activity recognition results from three perspectives;

The spatial discrimination is used to judge whether the stay space position of the travel target in the stay activity is correct; the evaluation method of the spatial discrimination is to determine whether the spatial range of the stop point identified by the stop recognition algorithm and the correct stop point are adjacent. , the evaluation index of the spatial discrimination is the proportion of the number of correct stop point samples within a given spatial range;

The space-time state discrimination is used to identify the stay space position of the travel target in the stay activity and the proportion of the corresponding stay duration; Whether the spatial range of the stop point and the correct stop point is adjacent, and the ratio of the length of stay of the identified stop point to the duration of the whole day; the evaluation index of the space-time state discrimination is the number of samples of the correct stop point in the given spatial range. The proportion and the proportion of the cumulative duration of the stay activity at the correct stop point;

The space-time object discrimination is used to identify the stop space position and stop start and end time of the travel target in the stop activity; the evaluation method of the space-time object discrimination is to determine the difference between the stop point and the stop point identified by the stop recognition algorithm. The spatial range of the correct stop point and whether the stop start and end times are adjacent; the evaluation index of the space-time object discrimination is the proportion of the number of correct stop point samples within a given space range and time range.
A stay identification evaluation system for mobile phone signaling data, characterized in that it includes:

Data collection module: used to collect the mobile phone signaling data and the corresponding GPS data of the travel target in the travel area;

Stop identification module: used to identify the stop activity of the travel target in the travel area by using the stop identification algorithm based on the mobile phone signaling data;

Stay evaluation module: used to construct a progressive stay recognition evaluation system based on the spatiotemporal sampling characteristics of mobile phone signaling data, and evaluate the stay activity recognition result of the travel target through the GPS data and the stay recognition evaluation system.
A terminal, characterized in that the terminal includes a processor and a memory coupled to the processor, wherein,

The memory stores a program instruction for realizing the method for evaluating the stop identification of mobile phone signaling data according to any one of claims 1-6;

The processor is configured to execute the program instructions stored in the memory to control dwell recognition evaluation for cell phone signaling data.
A storage medium, characterized in that it stores program instructions that are executable by a processor, and the program instructions are used to execute the method for evaluating the stop identification and evaluation of mobile phone signaling data according to any one of claims 1 to 6.